{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T03:28:43Z","timestamp":1782271723818,"version":"3.54.5"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:00:00Z","timestamp":1587340800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>In evidence-based medicine, defining a clinical question in terms of the specific patient problem aids the physicians to efficiently identify appropriate resources and search for the best available evidence for medical treatment. In order to formulate a well-defined, focused clinical question, a framework called PICO is widely used, which identifies the sentences in a given medical text that belong to the four components typically reported in clinical trials: Participants\/Problem (P), Intervention (I), Comparison (C) and Outcome (O). In this work, we propose a novel deep learning model for recognizing PICO elements in biomedical abstracts. Based on the previous state-of-the-art bidirectional long-short-term memory (bi-LSTM) plus conditional random field architecture, we add another layer of bi-LSTM upon the sentence representation vectors so that the contextual information from surrounding sentences can be gathered to help infer the interpretation of the current one. In addition, we propose two methods to further generalize and improve the model: adversarial training and unsupervised pre-training over large corpora.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We tested our proposed approach over two benchmark datasets. One is the PubMed-PICO dataset, where our best results outperform the previous best by 5.5%, 7.9% and 5.8% for P, I and O elements in terms of F1 score, respectively. And for the other dataset named NICTA-PIBOSO, the improvements for P\/I\/O elements are 3.9%, 15.6% and 1.3% in F1 score, respectively. Overall, our proposed deep learning model can obtain unprecedented PICO element detection accuracy while avoiding the need for any manual feature selection.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Code is available at https:\/\/github.com\/jind11\/Deep-PICO-Detection.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa256","type":"journal-article","created":{"date-parts":[[2020,4,14]],"date-time":"2020-04-14T19:14:52Z","timestamp":1586891692000},"page":"3856-3862","source":"Crossref","is-referenced-by-count":35,"title":["Advancing PICO element detection in biomedical text via deep neural networks"],"prefix":"10.1093","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9587-1698","authenticated-orcid":false,"given":"Di","family":"Jin","sequence":"first","affiliation":[{"name":"Compter Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology, Cambridge, MA 02139, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Szolovits","sequence":"additional","affiliation":[{"name":"Compter Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology, Cambridge, MA 02139, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,4,20]]},"reference":[{"key":"2023063011294982900_btaa256-B1","author":"Amini","year":"2012"},{"key":"2023063011294982900_btaa256-B2","first-page":"135","author":"Bojanowski","year":"2017"},{"key":"2023063011294982900_btaa256-B3","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/1472-6947-10-29","article-title":"Combining classifiers for robust pico element detection","volume":"10","author":"Boudin","year":"2010","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"2023063011294982900_btaa256-B5","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1186\/s12911-018-0699-2","article-title":"Combination of conditional random field with a rule based method in the extraction of pico elements","volume":"18","author":"Chabou","year":"2018","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"2023063011294982900_btaa256-B6","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J.\u00a0Mach. Learn. Res"},{"key":"2023063011294982900_btaa256-B7","first-page":"694","author":"Dernoncourt","year":"2017"},{"key":"2023063011294982900_btaa256-B8","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2023063011294982900_btaa256-B9","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/PROC.1973.9030","article-title":"The Viterbi algorithm","volume":"61","author":"Forney","year":"1973","journal-title":"Proc. IEEE"},{"key":"2023063011294982900_btaa256-B10","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1258\/jtt.2008.007007","article-title":"A method of extracting the number of trial participants from abstracts describing randomized controlled trials","volume":"14","author":"Hansen","year":"2008","journal-title":"J.\u00a0Telemed. Telecare"},{"key":"2023063011294982900_btaa256-B11","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.jbi.2014.02.006","article-title":"Identifying scientific artefacts in biomedical literature: the evidence based medicine use case","volume":"49","author":"Hassanzadeh","year":"2014","journal-title":"J.\u00a0Biomed. Inform"},{"key":"2023063011294982900_btaa256-B12","first-page":"359","volume-title":"AMIA Annual Symposium Proceedings","author":"Huang","year":"2006"},{"key":"2023063011294982900_btaa256-B13","first-page":"279","author":"Huang","year":"2011"},{"key":"2023063011294982900_btaa256-B14","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1016\/j.jbi.2013.07.009","article-title":"Pico element detection in medical text without metadata: are first sentences enough","volume":"46","author":"Huang","year":"2013","journal-title":"J.\u00a0Biomed. Inform"},{"key":"2023063011294982900_btaa256-B15","first-page":"67","author":"Jin","year":"2018"},{"key":"2023063011294982900_btaa256-B16","first-page":"1746","author":"Kim","year":"2014"},{"key":"2023063011294982900_btaa256-B17","first-page":"S5","author":"Kim","year":"2011"},{"key":"2023063011294982900_btaa256-B19","first-page":"1234","author":"Lee","year":"2020"},{"key":"2023063011294982900_btaa256-B20","author":"Lin","year":"2017"},{"key":"2023063011294982900_btaa256-B21","first-page":"134","author":"Lui","year":"2012"},{"key":"2023063011294982900_btaa256-B22","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Advances in Neural Information Processing Systems","author":"Mikolov","year":"2013"},{"key":"2023063011294982900_btaa256-B23","author":"Miyato","year":"2016"},{"key":"2023063011294982900_btaa256-B24","first-page":"1532","author":"Pennington","year":"2014"},{"key":"2023063011294982900_btaa256-B25","first-page":"2227","author":"Peters","year":"2018"},{"key":"2023063011294982900_btaa256-B26","doi-asserted-by":"crossref","first-page":"A12","DOI":"10.7326\/ACPJC-1995-123-3-A12","article-title":"The well-built clinical question: a key to evidence-based decisions","volume":"123","author":"Richardson","year":"1995","journal-title":"ACP J. Club"},{"key":"2023063011294982900_btaa256-B27","author":"Sarker","year":"2013"},{"key":"2023063011294982900_btaa256-B28","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/1472-6947-7-16","article-title":"Utilization of the pico framework to improve searching pubmed for clinical questions","volume":"7","author":"Schardt","year":"2007","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"2023063011294982900_btaa256-B29","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J.\u00a0Mach. Learn. Res"},{"key":"2023063011294982900_btaa256-B30","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2023063011294982900_btaa256-B31","first-page":"579","author":"Verbeke","year":"2012"},{"key":"2023063011294982900_btaa256-B32","first-page":"1480","author":"Yang","year":"2016"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa256\/33363807\/btaa256.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/12\/3856\/50750291\/bioinformatics_36_12_3856.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/12\/3856\/50750291\/bioinformatics_36_12_3856.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T11:30:08Z","timestamp":1688124608000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/12\/3856\/5822877"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,4,20]]},"references-count":30,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa256","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,6,15]]},"published":{"date-parts":[[2020,4,20]]}}}